Skip to content
Rival
Models
CompareBest ForArena
Sign Up
Sign Up

Compare AI vibes, not scores. Side-by-side outputs across the world's best models.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Leaderboard
  • Challenges

Discover

  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • .llmignore
  • Badges
  • RIVAL Datasets

Connect

  • Methodology
  • Sponsor
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival
Rival
Models
CompareBest ForArena
Sign Up
Sign Up

Compare AI vibes, not scores. Side-by-side outputs across the world's best models.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Leaderboard
  • Challenges

Discover

  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • .llmignore
  • Badges
  • RIVAL Datasets

Connect

  • Methodology
  • Sponsor
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival
  1. Home
  2. Models
  3. GPT-5.2 Chat
  4. Mini LBO Underwrite

See how GPT-5.2 Chat compares on this challenge:

  • GPT-5.2 Chat vs Claude Sonnet 4.6
  • GPT-5.2 Chat vs Gemini 3.1 Pro Preview
  • GPT-5.2 Chat vs Z.ai: GLM 5

4 models have responded to the "Mini LBO Underwrite" challenge. Compare their approaches side-by-side on RIVAL. This response is part of RIVAL's open dataset of 5,600+ AI model responses.

Rival
Models
CompareBest ForArena
Sign Up
Sign Up
Back to GPT-5.2 Chat

Mini LBO Underwrite

Gpt 5 2 Chat's response to the 'Mini LBO Underwrite' challenge.

GPT-5.2 Chat
February 8, 2026
Text

?
Prompt

You are underwriting a 5-year LBO for a private equity investment committee. Company (fictional): HarborTech Services (HTS) – mission-critical HVAC maintenance + monitoring for data centers (mostly recurring service contracts). Use only the information below. Do NOT browse the web. This is a fictional exercise. ENTRY (close at end of FY2025) - FY2025 revenue: $900m - FY2025 EBITDA: $120m (13.3% margin) - Purchase price: 12.0x EBITDA - Transaction fees: 2.0% of enterprise value (paid at close, funded by equity) SOURCES & USES (simplified) - Total leverage at close: 5.5x EBITDA - Term Loan: 4.0x EBITDA, 9.0% cash interest, 1.0% annual amortization - Mezzanine: 1.5x EBITDA, 12.0% cash interest + 2.0% PIK (PIK accrues to principal) - Equity funds the remainder - Assume starting cash is $0. - Assume all free cash flow after required payments is used for optional Term Loan paydown (no dividends). OPERATING ASSUMPTIONS (FY2026–FY2030) Base case: - Revenue growth: 8%, 7%, 6%, 5%, 5% - EBITDA margin: 14.0%, 15.0%, 16.0%, 16.5%, 17.0% - Capex: 3.0% of revenue - Change in NWC: 0.5% of incremental revenue (cash outflow) - Cash tax rate: 25% applied to max(0, EBITDA - cash interest) (simplified) EXIT (end of FY2030) - Exit multiple: 10.5x FY2030 EBITDA - Exit fees: 1.0% of enterprise value - Mezzanine (including PIK) is repaid at exit. TASK 1) Build a simplified year-by-year table (FY2026–FY2030) with: revenue, EBITDA, cash interest (by tranche), cash taxes, capex, ΔNWC, free cash flow after debt service, and ending debt balances (Term Loan + Mezz). 2) Compute equity IRR and MOIC. 3) Provide a sensitivity table of equity IRR vs exit multiple (9.5x / 10.5x / 11.5x) and exit-year EBITDA margin (16% / 17% / 18%). 4) List 5 underwriting risks and 5 concrete downside protection levers. Keep it concise, but show the math clearly.

GPT-5.2 Chat
Response

gpt-5.2-chat logo
GPT-5.2 ChatMini LBO Underwrite
gpt-5.2-chat logo
GPT-5.2 Chat

Below is a concise but fully worked underwriting using only your inputs. Minor rounding throughout.


1) Operating & Cash Flow Build (Base Case)

Entry (end FY2025)

  • EBITDA: $120m
  • EV @ 12.0x: $1,440m
  • Debt: $660m (TL $480m / Mezz $180m)
  • Fees (2% EV): $28.8m
  • Equity invested: $808.8m

Year-by-Year Summary ($mm)

FYRevenueEBITDACash Int (TL)Cash Int (Mezz)Cash TaxesCapexΔNWCFCF after req. payTerm Loan EndMezz End*
2026972.0136.143.221.617.829.20.419.1456.1183.6
20271,040.0156.041.022.023.331.20.333.4417.9187.3
20281,102.4176.437.622.529.133.10.349.0364.1191.0
20291,157.5191.032.822.933.834.70.361.7297.6194.8
20301,215.4206.626.823.439.136.50.375.7217.1198.7

*Mezz includes 2% annual PIK accrual.
All excess FCF is used for optional Term Loan paydown.
Mandatory amortization assumed at 1% of original TL ($4.8m/year).


2) Exit & Equity Returns

Exit (end FY2030)

  • EBITDA: $206.6m
  • Exit multiple: 10.5x
  • Exit EV: $2,169m
  • Exit fees (1%): (21.7)
  • Net EV: $2,147.3m

Debt repaid at exit

  • Term Loan: $217.1m
  • Mezz (incl. PIK): $198.7m
  • Total: $415.8m

Equity proceeds:
$2,147.3 − 415.8 = $1,731.5m

Returns

  • MOIC: 2.14x
  • 5‑yr IRR: ~16.5%

3) Equity IRR Sensitivity (%)

Rows = Exit EBITDA Margin (FY2030)
Columns = Exit Multiple

Exit Margin9.5x10.5x11.5x
16%~12.8%~14.6%~16.3%
17% (Base)~14.6%16.5%~18.3%
18%~16.3%~18.4%~20.5%

(Assumes same leverage path; EBITDA flexed via margin only.)


4) Key Underwriting Risks

  1. Customer concentration among hyperscale data center operators.
  2. Margin execution risk from labor inflation and technician availability.
  3. Technology displacement (AI-based predictive monitoring in-house by customers).
  4. Leverage sensitivity with meaningful mezz + PIK compounding.
  5. Exit multiple compression in infrastructure / services valuations.

5) Downside Protection Levers

  1. Tighter covenants & excess cash sweep to accelerate de-levering.
  2. Pricing escalators and CPI-linked clauses in service contracts.
  3. OpEx flexibility via subcontracting and variable labor mix.
  4. Capex deferral in non-critical monitoring upgrades.
  5. Early mezz refinance once leverage <4.0x to reduce cash + PIK drag.

Bottom line:
A defensible, cash-generative LBO with mid‑teens base‑case IRR, strong de‑levering, and meaningful upside from margin expansion and multiple stability.

Mini LBO Underwrite

Turn this model response into notes, narration, or a short video

Auto NotesTranscriptNarrateVideo Cut

Partner link

This output is part of our open dataset — 5K+ AI responses across 200 models

About GPT-5.2 Chat

Capabilities

ConversationReasoningCode GenerationAnalysis

Categories

TextCodeMultimodal

Specifications

Provider
Openai
Released
2025-12-10
Size
LARGE
Context
128,000 tokens

Keep exploring

SAME PROMPT

Claude Sonnet 4.6's version

Same prompt, different result

COMPARE

GPT-5.2 Chat vs Gemini 3.1 Pro Preview

Both outputs, side by side

Compare AI vibes, not scores. Side-by-side outputs across the world's best models.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Leaderboard
  • Challenges

Discover

  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • .llmignore
  • Badges
  • RIVAL Datasets

Connect

  • Methodology
  • Sponsor
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival